Paper Notes

标签: video-understanding

此标签下有5条笔记。

  • 2026年5月

    Lance: Unified Multimodal Modeling by Multi-Task Synergy

  • 2026年5月

    VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation

  • 2026年3月

    Attend Before Attention - Efficient and Scalable Video Understanding via Autoregressive Gazing

  • 2025年12月

    VL-JEPA: Joint Embedding Predictive Architecture for Vision-language

  • 2025年3月

    Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding


Created with Quartz v4.5.2 © 2026

  • Source